skill-share

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied metadata, such as skill names and descriptions, to generate file structures and Slack notifications. This creates a vulnerability surface where malicious input could influence downstream agent behavior or cause unexpected output in Slack messages.
  • Ingestion points: User-provided skill name and description inputs (SKILL.md).
  • Boundary markers: None identified in the provided instructions to delimit or neutralize user input.
  • Capability inventory: File system write operations for directory and file creation, and Slack integration tools including SLACK_SEND_MESSAGE and SLACK_POST_MESSAGE_WITH_BLOCKS (SKILL.md).
  • Sanitization: There are no instructions or scripts present to validate, escape, or sanitize the user-provided text before it is used to create files or sent to external Slack channels.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 03:47 PM
Security Audit — agent-trust-hub — skill-share